Key result
A multilayer perceptron algorithm using 33 multimodal physiological features achieved 75.61% accuracy in discriminating patients with panic disorder from healthy controls.
Why the study?
The authors tested the feasibility of automated discrimination of patients with panic disorder from healthy controls using machine learning based on multimodal physiological responses.
Can machine learning algorithms using multimodal physiological signals accurately differentiate patients with panic disorder from healthy controls?
Population
Patients with panic disorder and healthy controls
Comparison
Patients with panic disorder vs healthy controls
Authors
Loading...
ML-based PD discrimination from multimodal signals is feasible; leaves open clinical adoption pending larger prospective validation.
Observational
Can machine learning algorithms using multimodal physiological signals accurately differentiate patients with panic disorder from healthy controls?
Combining multimodal physiological signals measured during various states of autonomic arousal has the potential to differentiate patients with panic disorder from healthy controls using machine learning.
Choi et al. (2022) conducted an observational in Panic disorder. Multimodal physiological signals and machine learning algorithms vs. Healthy controls was evaluated on Accuracy of automated discrimination of panic disorder from healthy controls. A multilayer perceptron algorithm using 33 multimodal physiological features achieved 75.61% accuracy in discriminating patients with panic disorder from healthy controls.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: